ClawHub
Back to skill

Security audit

IDE Agent Kit

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent for IDE agent coordination, but its optional networking, command execution, credentials, and persistent state need careful configuration.

Before installing, verify the npm package and source, keep `tmux.allow` narrow, avoid committing or broadly sharing `ide-agent-kit.json` if it contains secrets, review every external URL used with `emit` or `hooks create`, and periodically check memory, queues, active sessions, and scheduled jobs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.